LLMs achieve higher accuracy than humans on compositional imagery tasks previously argued to require pictorial representations, supporting emergent propositional mental imagery in AI.
Shepard and Jacqueline Metzler
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Latent visual reasoning fails in current models because standard datasets make oracle latents uninformative and inference-time latents collapse away from useful representations.
citing papers explorer
-
Artificial Phantasia: Emergent Mental Imagery in Large Language Models
LLMs achieve higher accuracy than humans on compositional imagery tasks previously argued to require pictorial representations, supporting emergent propositional mental imagery in AI.
-
What's Holding Back Latent Visual Reasoning?
Latent visual reasoning fails in current models because standard datasets make oracle latents uninformative and inference-time latents collapse away from useful representations.